CN106156726B - The Enhancement Method and device of fingerprint image - Google Patents
The Enhancement Method and device of fingerprint image Download PDFInfo
- Publication number
- CN106156726B CN106156726B CN201610450915.1A CN201610450915A CN106156726B CN 106156726 B CN106156726 B CN 106156726B CN 201610450915 A CN201610450915 A CN 201610450915A CN 106156726 B CN106156726 B CN 106156726B
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- fingerprint image
- gray value
- fingerprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims description 10
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 238000005538 encapsulation Methods 0.000 description 3
- 230000001965 increasing effect Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000006641 stabilisation Effects 0.000 description 2
- 238000011105 stabilization Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Image Input (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses the Enhancement Method and device of a kind of fingerprint image, wherein, method includes：Collection user fingerprints simultaneously generate fingerprint image；Assignment treatment is carried out to fingerprint image, to obtain enhanced fingerprint image.The Enhancement Method of the fingerprint image of the embodiment of the present invention, the crestal line and valley line intensity contrast that can increase in fingerprint image are poor, the accuracy that fingerprint ridge directional information is asked in raising low quality fingerprint image, and then it is favorably improved the accuracy that fingerprint feature information is extracted, the validity that lifting fingerprint characteristic is compared.
Description
Technical field
The present invention relates to fingerprint identification technology field, and in particular to the Enhancement Method and device of a kind of fingerprint image.
Background technology
With the development of society, people propose requirement higher to the accuracy of authentication, security and practicality.
Traditional identification authentication mode, such as password, key, identity card, there are problems that easily forgetting, easily leakage, easy to lose, easily,
Therefore potential safety hazard is higher.Authentication based on biological characteristic, can overcome many shortcomings of traditional identity certification.Wherein,
Fingerprint because its have stability high, unique, easy collection, it is safe the features such as, comparatively ideal can be used for identity as one kind
The biological characteristic of certification.In actual use, fingerprint recognition system does not store fingerprint image directly typically, but from fingerprint image
In the characteristic information that takes the fingerprint, then carry out fingerprint matching identification, complete authentication.Therefore, reliability fingerprint high is extracted
Characteristic information is the key for ensureing correct identification fingerprint.
It is by the dynamic of gray value by following formula (1) when carrying out equalization processing to view picture fingerprint image in correlation technique
Scope is stretched, and the histogram to concentrating is equalized, to reach the effect of enhancing contrast.
G (i, j)=(C*255)/(M*N) (1)
Wherein, G (i, j) be change after pixel (i, j) gray value, C be conversion before gray value less than pixel (i,
The number of the pixel of gray value j), M*N is the number of the pixel in fingerprint image.
But the fingerprint image obtained by above-mentioned technology, it is impossible to exclude capacitance type fingerprint identification chip in itself, and it is extraneous
The interference that condition is produced.The fingerprint image of capacitance type sensor actual acquisition can contain noise, and noise information main source has biography
In itself, and water, oil, decortication on finger etc., these noise informations can cause that the fingerprint image for collecting is excessively black, mould to sensor
Paste, fracture, quality are low, if directly asking the direction to have difference with the actual texture trend of fingerprint with soble gradient method.And refer to
The encapsulation of line identification chip, coating etc. can cause chip surface uneven so that the fingerprint image gray value for collecting is not entirely same
Benchmark, can be to follow-up Finger print characteristic abstract, aspect ratio to there is interference.
The content of the invention
It is contemplated that at least solving one of technical problem in above-mentioned technology to a certain extent.Therefore, of the invention
First purpose is to propose a kind of Enhancement Method of fingerprint image.The method can increase crestal line and valley line ash in fingerprint image
Degree contrast differences, the accuracy that fingerprint ridge directional information is asked in raising low quality fingerprint image, and then help to extract more accurate
True fingerprint feature information, the validity that lifting fingerprint characteristic is compared.
Second object of the present invention is to propose a kind of intensifier of fingerprint image.
To reach above-mentioned purpose, first aspect present invention embodiment proposes a kind of Enhancement Method of fingerprint image, including
Following steps：Collection user fingerprints simultaneously generate fingerprint image；Assignment treatment is carried out to the fingerprint image, it is enhanced to obtain
Fingerprint image.
The Enhancement Method of the fingerprint image of the embodiment of the present invention, assignment treatment is carried out by fingerprint image, is strengthened
Fingerprint image afterwards, it is poor thereby, it is possible to increase the crestal line in fingerprint image and valley line intensity contrast, improve low quality fingerprint image
The accuracy that middle fingerprint ridge directional information is asked for, and then the accuracy of fingerprint feature information extraction is favorably improved, lifting refers to
The validity of line aspect ratio pair.
In addition, the Enhancement Method of finger print data according to the above embodiment of the present invention can also have following additional technology
Feature：
According to one embodiment of present invention, the fingerprint image includes M*N pixel being arranged in matrix, its
In, M, N are positive integer, described to carry out assignment treatment to the fingerprint image, to obtain enhanced fingerprint image, specific bag
Include：The gray value for counting pixel in the k*k neighborhoods centered on pixel (x, y) is less than or equal to the pixel (x, y)
Gray value pixel number num, wherein, the k is odd number, and described x, y are positive integer, and (k-1)/2<x≤M-(k-
1)/2, (k-1)/2<y≤N-(k-1)/2；The gray value of the pixel (x, y) is replaced by num*255/k2, to be increased
Fingerprint image after strong.
According to one embodiment of present invention, before assignment treatment is carried out to the fingerprint image, also include：To described
Fingerprint image is removed bad point treatment, to generate the first image；Treatment is filtered to described first image, to generate second
Image；3rd image is generated according to described first image and second image, the 3rd image is to carry out assignment treatment
Fingerprint image.
According to one embodiment of present invention, the fingerprint image includes M*N pixel being arranged in matrix, its
In, M, N be positive integer, wherein, it is described the fingerprint image is removed bad point treatment include：In calculating the fingerprint image
The average gray value of each pixel, wherein, the fingerprint image is gray level image；Judge the gray value of the pixel with it is right
Whether the absolute value of the difference of the average gray value answered is less than the first predetermined threshold value；If the gray value of the pixel with it is corresponding
Average gray value difference absolute value be more than or equal to first predetermined threshold value, then the gray value of the pixel is replaced
On behalf of corresponding average gray value.
According to one embodiment of present invention, the average gray value for calculating pixel (i, j) in the fingerprint image
Including：Calculate the not (a including the pixel (i, j) in the a*a neighborhoods centered on pixel (i, j)2- 1) individual pixel
The average gray value of point, wherein, i, j are positive integer, and a is odd number, and (a-1)/2<I≤M- (a-1)/2, (a-1)/2<j≤N-
(a-1)/2。
According to one embodiment of present invention, first predetermined threshold value is 40~60.
According to one embodiment of present invention, it is described that treatment is filtered to described first image, to generate the second image
Including：After carrying out the mean filter of m*m to described first image, then the mean filter of n*n is carried out, to generate second figure
Picture, wherein, the m is that, more than or equal to the odd number of a fingerprint line distance, the n is less than the odd number of the m.
According to one embodiment of present invention, it is described according to described first image and second image generate the 3rd image
Including：The gray value of each pixel in described first image is subtracted the ash of each pixel in corresponding second image
Angle value；Minimum value in the difference of the gray value of all pixels point that acquisition is calculated, and judge whether the minimum value is small
In 0；If the minimum value is less than 0, the difference of the gray value of all pixels point that will be calculated subtracts the minimum value,
To generate the 3rd image.
To reach above-mentioned purpose, second aspect present invention embodiment proposes a kind of intensifier of fingerprint image, including：
Collection generation module, for gathering user fingerprints and generating fingerprint image；First processing module, for entering to the fingerprint image
Row assignment treatment, to obtain enhanced fingerprint image.
The intensifier of the fingerprint image of the embodiment of the present invention, is carried out at assignment by first processing module to fingerprint image
Reason, obtains enhanced fingerprint image, poor thereby, it is possible to increase the crestal line in fingerprint image and valley line intensity contrast, improves low
The accuracy that fingerprint ridge directional information is asked in quality fingerprinting image, and then it is favorably improved the standard of fingerprint feature information extraction
True property, the validity that lifting fingerprint characteristic is compared.
In addition, the intensifier of fingerprint image according to the above embodiment of the present invention can also have following additional technology
Feature：
According to one embodiment of present invention, the fingerprint image includes M*N pixel being arranged in matrix, its
In, M, N are positive integer, wherein, the first processing module, including：Statistical module, for counting and being with pixel (x, y) in
Pixel is less than or equal to the number num of the pixel of the gray value of the pixel (x, y) in the k*k neighborhoods of the heart, wherein, institute
K is stated for odd number, described x, y are integer, and (k-1)/2<X≤M- (k-1)/2, (k-1)/2<y≤N-(k-1)/2；First substitutes
Module, for by num*255/k2The gray value of the pixel (x, y) is substituted, to obtain enhanced fingerprint image.
According to one embodiment of present invention, the intensifier of the fingerprint image, also includes：Second processing module, uses
In before the first processing module carries out assignment treatment to the fingerprint image, bad point is removed to the fingerprint image
Treatment, to generate the first image；3rd processing module, for being filtered treatment to described first image, to generate the second figure
Picture；Generation module, for generating the 3rd image according to described first image and second image, the 3rd image is to carry out
The fingerprint image of assignment treatment.
According to one embodiment of present invention, the fingerprint image includes M*N pixel being arranged in matrix, its
In, M, N are positive integer, wherein, the Second processing module, including：First computing module, for calculating the fingerprint image in
The average gray value of each pixel, wherein, the fingerprint image is gray level image；First judge module, it is described for judging
Whether the gray value of pixel is less than the first predetermined threshold value with the absolute value of the difference of corresponding average gray value；Second substitutes mould
Block, described first is more than or equal to for the gray value in the pixel with the absolute value of the difference of corresponding average gray value
During predetermined threshold value, the gray value of the pixel is replaced by corresponding average gray value.
According to one embodiment of present invention, first computing module specifically for：During calculating is with pixel (i, j)
Not (a including the pixel (i, j) in the a*a neighborhoods of the heart2- 1) average gray value of individual pixel, wherein, i, j are for just
Integer, a is odd number, and (a-1)/2<I≤M- (a-1)/2, (a-1)/2<j≤N-(a-1)/2.
According to one embodiment of present invention, first predetermined threshold value is 40~60.
According to one embodiment of present invention, the Second processing module, specifically for：M* is carried out to described first image
After the mean filter of m, then the mean filter of n*n is carried out, to generate second image, wherein, the m is more than or equal to one
The odd number of individual fingerprint line distance, the n is less than the odd number of the m.
According to one embodiment of present invention, the generation module, including：Second computing module, for by described first
The gray value of each pixel subtracts the gray value of each pixel in second image in image；Second judge module, uses
In after the minimum value in obtaining the difference of gray value of all pixels point being calculated, judge whether the minimum value is less than
0；3rd computing module, for when the minimum value is less than 0, the difference of the gray value of all pixels point that will be calculated to subtract
The minimum value is gone, to generate the 3rd image.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from description of the accompanying drawings below to embodiment is combined
Substantially and be readily appreciated that, wherein：
Fig. 1 is the flow chart of the Enhancement Method of fingerprint image according to embodiments of the present invention；
Fig. 2 is the flow chart of the Enhancement Method of fingerprint image according to an embodiment of the invention；
Fig. 3 be fingerprint image according to embodiments of the present invention Enhancement Method in step S202 flow chart；
Fig. 4 be fingerprint image according to embodiments of the present invention Enhancement Method in step S204 flow chart；
Fig. 5, Fig. 6, Fig. 7 are the contrast schematic diagrams of fingerprint image according to embodiments of the present invention；
Fig. 8 is the structured flowchart of the intensifier of fingerprint image according to embodiments of the present invention；
Fig. 9 is the structured flowchart of the intensifier of fingerprint image according to an embodiment of the invention；
Figure 10 is a structured flowchart for composition in the intensifier of fingerprint image according to embodiments of the present invention；
Figure 11 is the structured flowchart of another composition in the intensifier of fingerprint image according to embodiments of the present invention.
Specific embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from start to finish
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
It is exemplary to scheme the embodiment of description, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the Enhancement Method and device of the fingerprint image of the embodiment of the present invention described.
Fig. 1 is the flow chart of the Enhancement Method of fingerprint image according to embodiments of the present invention.As shown in figure 1, the fingerprint image
The Enhancement Method of picture includes：
S101, gathers user fingerprints and generates fingerprint image.
In an embodiment of the present invention, fingerprint image includes M*N pixel being arranged in matrix.
Wherein, M, N are positive integer.
S102, assignment treatment is carried out to fingerprint image, to obtain enhanced fingerprint image.
Specifically, pixel is less than or equal to picture in the k*k neighborhoods in statistics fingerprint image centered on pixel (x, y)
The number num of the pixel of the gray value of vegetarian refreshments (x, y), by num*255/k2The gray value of replacement pixels point (x, y), to obtain
Enhanced fingerprint image.
Wherein, in order to capture vegetarian refreshments is convenient, k is odd number, and x, y are positive integer, and (k-1)/2<X≤M- (k-1)/2, (k-
1)/2<y≤N-(k-1)/2。
Specifically, each pixel (x, y) in fingerprint image is processed.First, during selection is with pixel (x, y)
The regional extent of the k*k of the heart, crosses the border, and repartitions the region of k*k；Then, ash of the statistics less than or equal to pixel (x, y)
The number num, num*255/k of the pixel of angle value2As pixel in the corresponding enhanced fingerprint image of pixel (x, y)
The gray value of point；Each pixel poll one time in image, you can obtain enhanced fingerprint image.
Wherein, cross the border, if the region representation for repartitioning k*k can not be drawn centered on the pixel in fingerprint image
Point k*k regions, then ignore the pixel (keep the pixel gray value constant), divides k*k areas with other pixels again
Domain.
It should be noted that in an embodiment of the present invention, fingerprint image is gray level image.
The Enhancement Method of the fingerprint image of the embodiment of the present invention, assignment treatment is carried out by fingerprint image, is strengthened
Fingerprint image afterwards, poor thereby, it is possible to increase the crestal line in fingerprint image and valley line intensity contrast, the low quality that raising is obtained refers to
The accuracy of fingerprint ridge directional information in print image, and then help to extract more accurately fingerprint feature information, improve fingerprint
The validity of aspect ratio pair.
In one embodiment of the invention, as shown in Fig. 2 the Enhancement Method of the fingerprint image can also include：
S201, gathers user fingerprints and generates fingerprint image.
In an embodiment of the present invention, fingerprint image includes M*N pixel being arranged in matrix.
Wherein, M, N are positive integer.
S202, bad point treatment is removed to fingerprint image, to generate the first image.
Specifically, in one embodiment of the invention, as shown in figure 3, above-mentioned steps S102 is further included：
S2021, calculates the average gray value of each pixel in fingerprint image.
Wherein, fingerprint image is gray level image.
Specifically, the pixel (i, j) is not included in a*a neighborhoods of the calculating centered on pixel (i, j)
(a2- 1) average gray value of individual pixel, wherein, i, j are positive integer, and a is odd number, and (a-1)/2<I≤M- (a-1)/2,
(a-1)/2<j≤N-(a-1)/2。
Alternatively, the value of a can be 3.
It is understood that a*a neighborhood of the edge pixel point in fingerprint image not centered on it, then pixel at this
The gray value of point keeps constant.
S2022, judges whether the gray value of pixel is less than first with the absolute value of the difference of corresponding average gray value
Predetermined threshold value.
Wherein, the span of the first predetermined threshold value can be 40~60, such as 50.
S2023, if the absolute value of the gray value of pixel and the difference of corresponding average gray value is more than or equal to the
One predetermined threshold value, then be replaced by corresponding average gray value by the gray value of pixel.
Specifically, as shown in table 1 (a), the gray value 255 of central pixel point and corresponding average gray value (180+186
+ 196+187+193+178+200+190) absolute value 66.25 of/8 difference is more than the first predetermined threshold value 50, then and the pixel is
Bad point with other 8 average gray values of pixel 188.75, it is necessary to be replaced；As shown in table 1 (b), the gray scale of central pixel point
The absolute value 84.375 of value 5 and the difference of corresponding average gray value (85+80+96+87+100+69+78+120)/8 is more than the
One predetermined threshold value 50, then the pixel is bad point, it is necessary to be replaced with other 8 average gray values of pixel 89.375.Thus,
Bad point can be avoided to be extracted as the information of stabilization, reduce the possibility of misrecognition, while direction calculating can also be reduced
The generation of catastrophe, makes direction calculating result closer to the real-texture trend of fingerprint.
Table 1
If it should be noted that the absolute value of the gray value of pixel and the difference of corresponding average gray value is less than the
One predetermined threshold value, then keep the gray value of the pixel constant.
S203, treatment is filtered to the first image, to generate the second image.
Specifically, after the mean filter of m*m is carried out to the first image, then the mean filter of n*n is carried out, to generate the second figure
Picture.
Wherein, m is that, more than or equal to the odd number of a fingerprint line distance, value can be 9,11,13,15 or 17；N is
Odd number less than m, such as value can be 7.
S204, the 3rd image is generated according to the first image and the second image.
Specifically, in one embodiment of the invention, as shown in figure 4, step S204 can include：
S2041, the gray value of each pixel in the first image is subtracted the gray value of each pixel in the second image.
S2042, the minimum value in the difference of the gray value of all pixels point that acquisition is calculated, and judge that minimum value is
It is no to be less than 0.
S2043, if minimum value is less than 0, the difference of the gray value of all pixels point that will be calculated subtracts minimum
Value, to generate the 3rd image.
In one embodiment of the invention, if minimum value is more than or equal to 0, each pixel in the first image
Gray value subtracts the image generated after the gray value of each pixel in corresponding second image and is the 3rd image.
In an embodiment of the present invention, by above-mentioned steps S203 and S204, capacitance type fingerprint chip can effectively be reduced
During collection image, chip coating, the uneven interference for bringing of encapsulation make the fingerprint image gray value of collection all in same benchmark,
And then it is favorably improved the accuracy of follow-up result of calculation.
S205, assignment treatment is carried out to the 3rd image, to obtain enhanced fingerprint image.
Specifically, pixel is less than or equal to picture in the k*k neighborhoods in the 3rd image of statistics centered on pixel (x, y)
The number num of the pixel of the gray value of vegetarian refreshments (x, y), by num*255/k2The gray value of replacement pixels point (x, y), to obtain
Enhanced fingerprint image.
Wherein, in order to capture vegetarian refreshments is convenient, k is odd number, and x, y are integer, and (k-1)/2<X≤M- (k-1)/2, (k-1)/
2<y≤N-(k-1)/2。
Specifically, each pixel (x, y) in the 3rd image is processed.First, during selection is with pixel (x, y)
The regional extent of the k*k of the heart, crosses the border, and repartitions the region of k*k；Then, ash of the statistics less than or equal to pixel (x, y)
The number num, num*255/k of the pixel of angle value2As pixel in the corresponding enhanced fingerprint image of pixel (x, y)
The gray value of point；Each pixel poll one time in image, you can obtain enhanced fingerprint image.
Wherein, cross the border, if the region representation for repartitioning k*k can not be drawn centered on the pixel in the 3rd image
Point k*k regions, then ignore the pixel (keep the pixel gray value constant), divides k*k areas with other pixels again
Domain.
For example, in one embodiment of the invention, Fig. 5 (a) is the original fingerprint image for gathering and generating, Fig. 5
B () is corresponding by the enhanced fingerprint image of the above method of the invention.As can be seen that phase in image shown in Fig. 5 (b)
Gray scale difference contrast between adjacent crestal line, valley line becomes apparent from.
In another embodiment of the present invention, Fig. 6 (a) is the original fingerprint image for gathering and generating, and Fig. 6 (b) is right
Answer by the enhanced fingerprint image of the above method of the invention.As can be seen that adjacent crestal line in image shown in Fig. 6 (b),
The contrast benchmark of valley line is identical, and gray scale difference level is identical.
There is one embodiment of the invention, Fig. 7 (a) is the original fingerprint image that gathers and generate, Fig. 7 (b) is original
The corresponding direction calculating result images of beginning fingerprint image, Fig. 7 (c) is that original fingerprint image is corresponding by above-mentioned side of the invention
The enhanced fingerprint image of method, Fig. 7 (d) is the corresponding direction calculating result images of enhanced fingerprint image.As can be seen that increasing
Fingerprint image after strong is more more consistent than the direction result of original fingerprint image, with the true trend of streakline closer to.
Thus, processed by being removed bad point to fingerprint image, to generate the first image, and the first image is filtered
Treatment, to generate the second image, and then generates the 3rd image according to the first image and the second image, is carried out by the 3rd image
Assignment treatment, obtains enhanced fingerprint image, thereby, it is possible to make the fingerprint image gray value for collecting all in same base
Standard, the crestal line and valley line intensity contrast in increase fingerprint image is poor, fingerprint ridge side in the low quality fingerprint image that raising is obtained
To the accuracy of information, and then help to extract more accurately fingerprint feature information, improve the validity that fingerprint characteristic is compared.
Fig. 8 is the structured flowchart of the intensifier of the fingerprint image of the embodiment of the present invention.As shown in figure 8, the fingerprint image
Intensifier include：Collection generation module 10 and first processing module 20.
Wherein, collection generation module 10 is used to gather user fingerprints and generates fingerprint image.
In an embodiment of the present invention, fingerprint image includes M*N pixel being arranged in matrix.
Wherein, M, N are positive integer.
First processing module 20 is used to carry out assignment treatment to fingerprint image, to obtain enhanced fingerprint image.
Specifically, first processing module 20 is further included：The alternative module 22 of statistical module 21 and first.
Wherein, statistical module 21 is used to count pixel in the k*k neighborhoods in fingerprint image centered on pixel (x, y)
Less than or equal to the number num of the pixel of the gray value of pixel (x, y).
Wherein, k is odd number, and x, y are positive integer, and (k-1)/2<X≤M- (k-1)/2, (k-1)/2<y≤N-(k-1)/2.
First alternative module 52 is used for num*255/k2The gray value of replacement pixels point (x, y), it is enhanced to obtain
Fingerprint image.
Specifically, each pixel (x, y) in fingerprint image is processed.Selection is centered on pixel (x, y)
The regional extent of k*k, crosses the border, and repartitions the region of k*k；Counted by statistical module 21 and be less than or equal to pixel (x, y)
Gray value pixel number num, by the first alternative module 22 by num*255/k2It is replaced by pixel (x, y) correspondence
Enhanced fingerprint image in the pixel gray value；Each pixel poll one time in image, you can after being strengthened
Fingerprint image.
Wherein, cross the border, if the region representation for repartitioning k*k can not be drawn centered on the pixel in fingerprint image
Point k*k regions, then ignore the pixel (keep the pixel gray value constant), divides k*k areas with other pixels again
Domain.
It should be noted that above-mentioned fingerprint image is gray level image.
The intensifier of the fingerprint image of the embodiment of the present invention, is carried out at assignment by first processing module to fingerprint image
Reason, obtains enhanced fingerprint image, and poor thereby, it is possible to increase the crestal line in fingerprint image and valley line intensity contrast, raising is asked
The accuracy of fingerprint ridge directional information in the low quality fingerprint image for going out, and then help to extract more accurately fingerprint characteristic letter
Breath, improves the validity that fingerprint characteristic is compared.
In one embodiment of the invention, as shown in figure 9, the intensifier of the fingerprint image includes：Collection generation mould
Block 10, first processing module 20, Second processing module 30, the 3rd processing module 40 and generation module 50.
Wherein, collection generation module 10 is used to gather user fingerprints and generates fingerprint image.
In an embodiment of the present invention, fingerprint image includes M*N pixel being arranged in matrix.
Wherein, M, N are positive integer.
Second processing module 30 is used to be removed fingerprint image bad point treatment, to generate the first image.
Specifically, in one embodiment of the invention, as shown in Figure 10, first processing module 30 is further included：The
One computing module 31, the first judge module 32 and the second alternative module 33.
Wherein, the first computing module 31 is used to calculate the average gray value of each pixel in fingerprint image, wherein, fingerprint
Image is gray level image.
Specifically, the first computing module 31 is calculated in the a*a neighborhoods centered on pixel (i, j) does not include pixel
(a of (i, j)2- 1) average gray value of individual pixel, wherein, i, j are positive integer, and a is odd number, and (a-1)/2<i≤M-(a-
1)/2, (a-1)/2<j≤N-(a-1)/2.
Alternatively, the value of a can be 3.
It is understood that a*a neighborhood of the edge pixel point in fingerprint image not centered on it, then pixel at this
The gray value of point keeps constant.
First judge module 32 is used to judge the absolute value of the gray value with the difference of corresponding average gray value of pixel
Whether the first predetermined threshold value is less than.
Wherein, the span of the first predetermined threshold value can be 40~60, such as 50.
Second alternative module 33 is used for big with the absolute value of the difference of corresponding average gray value in the gray value of pixel
When the first predetermined threshold value, the gray value of pixel is replaced by corresponding average gray value.
Specifically, as shown in table 1 (a), the gray value 255 of central pixel point and corresponding average gray value (180+186
+ 196+187+193+178+200+190) absolute value 66.25 of/8 difference is more than the first predetermined threshold value 50, then and the pixel is
Bad point with other 8 average gray values of pixel 188.75, it is necessary to be replaced；As shown in table 1 (b), the gray scale of central pixel point
The absolute value 84.375 of value 5 and the difference of corresponding average gray value (85+80+96+87+100+69+78+120)/8 is more than the
One predetermined threshold value 50, then the pixel is bad point, it is necessary to be replaced with other 8 average gray values of pixel 89.375.Thus,
Bad point can be avoided to be extracted as the information of stabilization, reduce the possibility of misrecognition, while direction calculating can also be reduced
The generation of catastrophe, makes direction calculating result closer to the real-texture trend of fingerprint.
Table 1
If it should be noted that the absolute value of the gray value of pixel and the difference of corresponding average gray value is less than the
One predetermined threshold value, then keep the gray value of the pixel constant.
3rd processing module 40 is used to be filtered treatment to the first image, to generate the second image.
Specifically, after 40 pairs of the first images of the 3rd processing module carry out the mean filter of m*m, then the average filter for carrying out n*n
Ripple, to generate the second image.
Wherein, m is that, more than or equal to the odd number of a fingerprint line distance, value can be 9,11,13,15 or 17；N is
Odd number less than m, such as value can be 7.
Generation module 50 is used to generate the 3rd image according to the first image and the second image.
Specifically, in one embodiment of the invention, as shown in figure 11, generation module 50 is further included：Second meter
Calculate module 51, the second judge module 52 and the 3rd computing module 53.
During second computing module 51 is used to for the gray value of each pixel in the first image to subtract corresponding second image
The gray value of each pixel.
The minimum value that second judge module 52 is used in the difference of gray value of all pixels point being calculated is obtained
Afterwards, judge minimum value whether less than 0.
3rd computing module 43 is used for when minimum value is less than 0, the difference of the gray value of all pixels point that will be calculated
Value subtracts minimum value, to generate the 3rd image.
In one embodiment of the invention, if minimum value is more than or equal to 0, each pixel in the first image
Gray value subtracts the image generated after the gray value of each pixel in the second image and is the 3rd image.
In an embodiment of the present invention, by above-mentioned Second processing module 40 and generation module 50, electricity can effectively be reduced
During appearance formula fingerprint chip collection image, chip coating, the uneven interference for bringing of encapsulation make the fingerprint image gray value whole of collection
In same benchmark, and then it is favorably improved the accuracy of follow-up result of calculation.
First processing module 20 is used to carry out assignment treatment to the 3rd image, to obtain enhanced fingerprint image.
Specifically, statistical module 21 is used for pixel in the k*k neighborhoods in the 3rd image of statistics centered on pixel (x, y)
Number num of the point less than or equal to the pixel of the gray value of pixel (x, y).
Wherein, k is odd number, and x, y are positive integer, and (k-1)/2<X≤M- (k-1)/2, (k-1)/2<y≤N-(k-1)/2.
First alternative module 22 is used for num*255/k2The gray value of replacement pixels point (x, y), it is enhanced to obtain
Fingerprint image.
Specifically, each pixel (x, y) in the 3rd image is processed.Selection is centered on pixel (x, y)
The regional extent of k*k, crosses the border, and repartitions the region of k*k；Counted by statistical module 21 and be less than or equal to pixel (x, y)
Gray value pixel number num, by the first alternative module 22 by num*255/k2It is replaced by pixel (x, y) correspondence
Enhanced fingerprint image in the pixel gray value；Each pixel poll one time in image, you can after being strengthened
Fingerprint image.
Wherein, cross the border, if the region representation for repartitioning k*k can not be drawn centered on the pixel in the 3rd image
Point k*k regions, then ignore the pixel (keep the pixel gray value constant), divides k*k areas with other pixels again
Domain.
For example, in one embodiment of the invention, Fig. 4 (a) is the original fingerprint image for gathering and generating, Fig. 4
B () is corresponding by the enhanced fingerprint image of said apparatus of the invention.As can be seen that phase in image shown in Fig. 4 (b)
Gray scale difference contrast between adjacent crestal line, valley line becomes apparent from.
In another embodiment of the present invention, Fig. 5 (a) is the original fingerprint image for gathering and generating, and Fig. 5 (b) is right
Answer by the enhanced fingerprint image of said apparatus of the invention.As can be seen that adjacent crestal line in image shown in Fig. 5 (b),
The contrast benchmark of valley line is identical, and gray scale difference level is identical.
There is one embodiment of the invention, Fig. 6 (a) is the original fingerprint image that gathers and generate, Fig. 6 (b) is original
The corresponding direction calculating result images of beginning fingerprint image, Fig. 6 (c) is that original fingerprint image is corresponding by above-mentioned dress of the invention
Enhanced fingerprint image is put, Fig. 6 (d) is the corresponding direction calculating result images of enhanced fingerprint image.As can be seen that increasing
Fingerprint image after strong is more more consistent than the direction result of original fingerprint image, with the true trend of streakline closer to.
Thus, bad point is removed to fingerprint image by Second processing module to process, to generate the first image, and pass through
3rd the first image of processing module is filtered treatment, to generate the second image, and then by generation module according to the first image
The 3rd image is generated with the second image, assignment treatment is carried out to the 3rd image by first processing module, obtain enhanced finger
Print image, thereby, it is possible to make crestal line all in same benchmark, increase fingerprint image of the fingerprint image gray value that collects and
Valley line intensity contrast is poor, the accuracy of fingerprint ridge directional information in the low quality fingerprint image that raising is obtained, and then contributes to
More accurately fingerprint feature information is extracted, the validity that fingerprint characteristic is compared is improved.
In the description of the invention, it is to be understood that term " " center ", " on ", D score, "front", "rear", " left side ",
The orientation or position relationship of the instruction such as " right side ", " vertical ", " level ", " top ", " bottom " " interior ", " outward " are based on side shown in the drawings
Position or position relationship, are for only for ease of the description present invention and are described with simplified, rather than the device or unit that indicate or imply meaning
Part with specific orientation, with specific azimuth configuration and operation, therefore must be not considered as limiting the invention.
Additionally, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In the description of the invention, " multiple " is meant that at least two, such as two, three
It is individual etc., unless otherwise expressly limited specifically.
In the present invention, unless otherwise clearly defined and limited, fisrt feature second feature " on " or D score can be with
It is the first and second feature directly contacts, or the first and second features are by intermediary mediate contact.And, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature are directly over second feature or oblique upper, or be merely representative of
Fisrt feature level height is higher than second feature.Fisrt feature second feature " under ", " lower section " and " below " can be
One feature is immediately below second feature or obliquely downward, or is merely representative of fisrt feature level height less than second feature.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or spy that the embodiment or example are described
Point is contained at least one embodiment of the invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.And, the specific features of description, structure, material or feature can be with office
Combined in an appropriate manner in one or more embodiments or example.Additionally, in the case of not conflicting, the skill of this area
Art personnel can be tied the feature of the different embodiments or example described in this specification and different embodiments or example
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (14)
1. a kind of Enhancement Method of fingerprint image, it is characterised in that：
Collection user fingerprints simultaneously generate fingerprint image, wherein, the fingerprint image includes M*N pixel being arranged in matrix
Point, M, N are positive integer；
The gray value for counting pixel in the k*k neighborhoods centered on pixel (x, y) is less than or equal to the pixel (x, y)
Gray value pixel number num, wherein, k is odd number, and x, y are positive integer, and (k-1)/2<X≤M- (k-1)/2, (k-
1)/2<y≤N-(k-1)/2；
The gray value of the pixel (x, y) is replaced by num*255/k2, to obtain enhanced fingerprint image.
2. the Enhancement Method of fingerprint image as claimed in claim 1, it is characterised in that assignment is being carried out to the fingerprint image
Before treatment, also include：
Bad point treatment is removed to the fingerprint image, to generate the first image；
Treatment is filtered to described first image, to generate the second image；
3rd image is generated according to described first image and second image, the 3rd image is the finger for carrying out assignment treatment
Print image.
3. the Enhancement Method of fingerprint image as claimed in claim 2, it is characterised in that the fingerprint image is included with rectangular
M*N pixel of formula arrangement, wherein, M, N are positive integer, wherein, it is described that bad point treatment is removed to the fingerprint image
Including：
The average gray value of each pixel in the fingerprint image is calculated, wherein, the fingerprint image is gray level image；
Judge whether the gray value of the pixel presets threshold less than first with the absolute value of the difference of corresponding average gray value
Value；
If the gray value of the pixel is more than or equal to described first with the absolute value of the difference of corresponding average gray value
Predetermined threshold value, then be replaced by corresponding average gray value by the gray value of the pixel.
4. the Enhancement Method of fingerprint image as claimed in claim 3, it is characterised in that picture in the calculating fingerprint image
The average gray value of vegetarian refreshments (i, j) includes：
Calculate the not (a including the pixel (i, j) in the a*a neighborhoods centered on pixel (i, j)2- 1) individual pixel
Average gray value, wherein, i, j are positive integer, and a is odd number, and (a-1)/2<I≤M- (a-1)/2, (a-1)/2<j≤N-(a-
1)/2。
5. the Enhancement Method of fingerprint image as claimed in claim 4, it is characterised in that the value model of first predetermined threshold value
Enclose is 40~60.
6. the Enhancement Method of fingerprint image as claimed in claim 2, it is characterised in that described to be filtered to described first image
Ripple treatment, is included with generating the second image：
After carrying out the mean filter of m*m to described first image, then the mean filter of n*n is carried out, to generate second image,
Wherein, the m is that, more than or equal to the odd number of a fingerprint line distance, the n is less than the odd number of the m.
7. the Enhancement Method of fingerprint image as claimed in claim 2, it is characterised in that described according to described first image and institute
Stating the second image the 3rd image of generation includes：
The gray value of each pixel in described first image is subtracted the ash of each pixel in corresponding second image
Angle value；
Minimum value in the difference of the gray value of all pixels point that acquisition is calculated, and judge whether the minimum value is less than
0；
If the minimum value is less than 0, the difference of the gray value of all pixels point that will be calculated subtracts the minimum value,
To generate the 3rd image.
8. a kind of intensifier of fingerprint image, it is characterised in that including：
Collection generation module, for gathering user fingerprints and generating fingerprint image, wherein, the fingerprint image is included with rectangular
M*N pixel of formula arrangement, M, N are positive integer；
First processing module, the first processing module includes：
Statistical module, the pixel is less than or equal to for counting pixel in the k*k neighborhoods centered on pixel (x, y)
The number num of the pixel of the gray value of (x, y), wherein, k is odd number, and x, y are integer, and (k-1)/2<X≤M- (k-1)/2,
(k-1)/2<Y≤N- (k-1)/2,
First alternative module, for by num*255/k2The gray value of the pixel (x, y) is substituted, to obtain enhanced finger
Print image.
9. the intensifier of fingerprint image as claimed in claim 8, it is characterised in that also include：
Second processing module, for before the first processing module carries out assignment treatment to the fingerprint image, to described
Fingerprint image is removed bad point treatment, to generate the first image；
3rd processing module, for being filtered treatment to described first image, to generate the second image；
Generation module, for generating the 3rd image according to described first image and second image, the 3rd image be into
The fingerprint image of row assignment treatment.
10. the intensifier of fingerprint image as claimed in claim 9, it is characterised in that the fingerprint image is included with matrix
Form arrangement M*N pixel, wherein, M, N be positive integer, the Second processing module, including：
First computing module, the average gray value for calculating each pixel in the fingerprint image, wherein, the fingerprint image
As being gray level image；
First judge module, the gray value for judging the pixel is with the absolute value of the difference of corresponding average gray value
It is no to be less than the first predetermined threshold value；
Second alternative module, is more than for the gray value in the pixel with the absolute value of the difference of corresponding average gray value
Or during equal to first predetermined threshold value, the gray value of the pixel is replaced by corresponding average gray value.
The intensifier of 11. fingerprint images as claimed in claim 10, it is characterised in that first computing module is specifically used
In：
Calculate the not (a including the pixel (i, j) in the a*a neighborhoods centered on pixel (i, j)2- 1) individual pixel
Average gray value, wherein, i, j are positive integer, and a is odd number, and (a-1)/2<I≤M- (a-1)/2, (a-1)/2<j≤N-(a-
1)/2。
The intensifier of 12. fingerprint images as claimed in claim 11, it is characterised in that first predetermined threshold value be 40~
60。
The intensifier of 13. fingerprint images as claimed in claim 9, it is characterised in that the Second processing module, it is specific to use
In：
After carrying out the mean filter of m*m to described first image, then the mean filter of n*n is carried out, to generate second image,
Wherein, the m is that, more than or equal to the odd number of a fingerprint line distance, the n is less than the odd number of the m.
The intensifier of 14. fingerprint images as claimed in claim 9, it is characterised in that the generation module, including：
Second computing module, for the gray value of each pixel in described first image to be subtracted into each in second image
The gray value of pixel；
Second judge module, for after the minimum value in obtaining the difference of gray value of all pixels point being calculated, sentencing
Whether the minimum value of breaking is less than 0；
3rd computing module, for the minimum value be less than 0 when, the difference of the gray value of all pixels point that will be calculated
The minimum value is subtracted, to generate the 3rd image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610450915.1A CN106156726B (en) | 2016-06-20 | 2016-06-20 | The Enhancement Method and device of fingerprint image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610450915.1A CN106156726B (en) | 2016-06-20 | 2016-06-20 | The Enhancement Method and device of fingerprint image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106156726A CN106156726A (en) | 2016-11-23 |
| CN106156726B true CN106156726B (en) | 2017-07-04 |
Family
ID=57353517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610450915.1A Active CN106156726B (en) | 2016-06-20 | 2016-06-20 | The Enhancement Method and device of fingerprint image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106156726B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815821B (en) * | 2017-01-23 | 2020-08-28 | 上海兴芯微电子科技有限公司 | Denoising method and device for near-infrared image |
| CN108701218B (en) * | 2017-02-03 | 2021-02-12 | 华为技术有限公司 | Fingerprint acquisition method and device and terminal |
| CN109426795A (en) * | 2017-09-05 | 2019-03-05 | 比亚迪股份有限公司 | Fingerprint identification method and device |
| CN107832473A (en) * | 2017-11-30 | 2018-03-23 | 奕响（大连）科技有限公司 | A kind of picture similar decision method after non-equal proportion stretching |
| CN107886134A (en) * | 2017-11-30 | 2018-04-06 | 奕响（大连）科技有限公司 | A kind of local creative similar decision method of picture |
| CN108124483B (en) | 2017-12-01 | 2022-06-07 | 深圳市汇顶科技股份有限公司 | Fingerprint image enhancement method and fingerprint image module |
| CN112884756A (en) * | 2021-03-12 | 2021-06-01 | 敦泰电子（深圳）有限公司 | Fingerprint image processing method, fingerprint chip and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100752640B1 (en) * | 2005-01-05 | 2007-08-29 | 삼성전자주식회사 | Method and apparatus for segmenting fingerprint region using directional gradient filters |
| CN101576999B (en) * | 2009-06-01 | 2012-10-17 | 杭州晟元芯片技术有限公司 | Fingerprint image orientation enhancement method |
| CN102254163A (en) * | 2011-08-03 | 2011-11-23 | 山东志华信息科技股份有限公司 | Template size self-adaptable Gabor fingerprint image enhancement method |
-
2016
- 2016-06-20 CN CN201610450915.1A patent/CN106156726B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106156726A (en) | 2016-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156726B (en) | The Enhancement Method and device of fingerprint image | |
| CN101901336B (en) | Fingerprint and finger vein bimodal recognition decision level fusion method | |
| CN110097034A (en) | A kind of identification and appraisal procedure of Intelligent human-face health degree | |
| CN102629316B (en) | Image enhancement method in automatic fingerprint identification technology | |
| JP4237145B2 (en) | Biological information detection device | |
| CN105631272B (en) | A kind of identity identifying method of multiple security | |
| CN105518716A (en) | Finger vein recognition method and apparatus | |
| CN103218605B (en) | A kind of fast human-eye positioning method based on integral projection and rim detection | |
| CN108764093B (en) | Non-contact fingerprint image acquisition device and method based on camera | |
| CN103324944A (en) | Fake fingerprint detecting method based on SVM and sparse representation | |
| CN102142080A (en) | Biometric authentication apparatus, biometric authentication method, and program | |
| CN105139404A (en) | Identification camera capable of detecting photographing quality and photographing quality detecting method | |
| CN101615241B (en) | Method for screening certificate photos | |
| CN101681497A (en) | Vein pattern management system, vein pattern registration device, vein pattern authentication device, vein pattern registration method, vein pattern authentication method, program, and vein data struc | |
| WO2017161636A1 (en) | Fingerprint-based terminal payment method and device | |
| Bhowmik et al. | Fingerprint Image Enhancement And It‟ s Feature Extraction For Recognition | |
| Lu et al. | A pore-based method for fingerprint liveness detection | |
| Espinoza et al. | Risk evaluation for spoofing against a sensor supplied with liveness detection | |
| CN106203322A (en) | A kind of identity authorization system based on hand back vein and palmmprint fusion image and method | |
| JP5669572B2 (en) | Fingerprint authentication device | |
| WO2018196521A1 (en) | Quality score calculation method and device for finger vein image | |
| Devadoss et al. | Performance improvement using an automation system for recognition of multiple parametric features based on human footprint | |
| CN104573628A (en) | Three-dimensional face recognition method | |
| Kumar et al. | Performance improvement using an automation system for segmentation of multiple parametric features based on human footprint | |
| CN209640873U (en) | A kind of finger vein image imaging device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191231 Address after: 518119 1 Yanan Road, Kwai Chung street, Dapeng New District, Shenzhen, Guangdong Patentee after: SHENZHEN BYD MICROELECTRONICS Co.,Ltd. Address before: BYD 518118 Shenzhen Road, Guangdong province Pingshan New District No. 3009 Patentee before: BYD Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 518119 No.1 Yan'an Road, Kuiyong street, Dapeng New District, Shenzhen City, Guangdong Province Patentee after: BYD Semiconductor Co.,Ltd. Address before: 518119 No.1 Yan'an Road, Kuiyong street, Dapeng New District, Shenzhen City, Guangdong Province Patentee before: BYD Semiconductor Co.,Ltd. Address after: 518119 No.1 Yan'an Road, Kuiyong street, Dapeng New District, Shenzhen City, Guangdong Province Patentee after: BYD Semiconductor Co.,Ltd. Address before: 518119 No.1 Yan'an Road, Kuiyong street, Dapeng New District, Shenzhen City, Guangdong Province Patentee before: SHENZHEN BYD MICROELECTRONICS Co.,Ltd. |